Masterthesis script, weerparameters
Heleen Van Ransbeeck
2023-01-03
Data inladen
Baits<-read.table(file = "~/GitHub/vespa_analyses/Input/Baits_useful.txt", header=TRUE, sep="\t", na.strings=c(""," ","NA"))
Flights_incomplete<-read.table(file = "~/GitHub/vespa_analyses/Input/Flights_incomplete.txt", header=TRUE, sep="\t", na.strings=c(""," ","NA"))
Nests<-read.table(file = "~/GitHub/vespa_analyses/Input/Nests_useful.txt", header=TRUE, sep="\t", na.strings=c(""," ","NA"))
Shortind_incomplete<-read.table(file = "~/GitHub/vespa_analyses/Input/Shortind_incomplete.txt", header=TRUE, sep="\t", na.strings=c(""," ","NA"))
Shortpot_incomplete<-read.table(file = "~/GitHub/vespa_analyses/Input/Shortpot_incomplete.txt", header=TRUE, sep="\t", na.strings=c(""," ","NA"))
Individuals<-read.table(file = "~/GitHub/vespa_analyses/Input/Individuals.txt", header=TRUE, sep="\t", na.strings=c(""," ","NA"))-incomplete wil zeggen dat de weergegevens nog niet volledig zijn. Ik wacht hiervoor op het KMI.
Aanpassingen datasets
# Overbodige kolommen wegdoen, foutje in excel
Flights_incomplete<-Flights_incomplete[1:(length(Flights_incomplete)-2)]
Shortind_incomplete<-Shortind_incomplete[1:(length(Shortind_incomplete)-2)]
Shortpot_incomplete<-Shortpot_incomplete[1:(length(Shortpot_incomplete)-2)]
#Foerageersnelheid en vliegsnelheid (m/s) toevoegen aan tabel
Flights_incomplete$test_rule_of_thumb<-Flights_incomplete$Distance/(Flights_incomplete$Flighttime_min*60)
Shortind_incomplete$test_rule_of_thumb<-Shortind_incomplete$Distance/(Shortind_incomplete$Flighttime_min*60)
Shortpot_incomplete$test_rule_of_thumb<-Shortpot_incomplete$Distance/(Shortpot_incomplete$Flighttime_min*60)
Flights_incomplete$ForagingSpeed<-Flights_incomplete$Distance*2/(Flights_incomplete$Flighttime_min*60)
Shortind_incomplete$ForagingSpeed<-Shortind_incomplete$Distance*2/(Shortind_incomplete$Flighttime_min*60)
Shortpot_incomplete$ForagingSpeed<-Shortpot_incomplete$Distance*2/(Shortpot_incomplete$Flighttime_min*60)
## Urbanisatiecirkels per vliegtijd toevoegen
Flights_incomplete<-merge(Flights_incomplete, Baits[, c("NestID", "BaitID", "Urbanisation25m", "Urbanisation50m", "Urbanisation100m")], by=c("NestID", "BaitID"), all=TRUE)
Shortind_incomplete<-merge(Shortind_incomplete, Baits[, c("NestID", "BaitID", "Urbanisation25m", "Urbanisation50m", "Urbanisation100m")], by=c("NestID", "BaitID"))
Shortpot_incomplete<-merge(Shortpot_incomplete, Baits[, c("NestID", "BaitID", "Urbanisation25m", "Urbanisation50m", "Urbanisation100m")], by=c("NestID", "BaitID"))
## Urbanisatietrajecten per vliegtijd toevoegen
Flights_incomplete<-merge(Flights_incomplete, Baits[, c("NestID", "BaitID", "Traject25m", "Traject50m", "Traject100m")], by=c("NestID", "BaitID"), all=TRUE)
Shortind_incomplete<-merge(Shortind_incomplete, Baits[, c("NestID", "BaitID", "Traject25m", "Traject50m", "Traject100m")], by=c("NestID", "BaitID"))
Shortpot_incomplete<-merge(Shortpot_incomplete, Baits[, c("NestID", "BaitID", "Traject25m", "Traject50m", "Traject100m")], by=c("NestID", "BaitID"))
## Gewicht individu per vliegtijd toevoegen
Flights_incomplete<-merge(Flights_incomplete, Individuals[, c("NestID", "BaitID","ColorInd", "Weight_ind")], by=c("NestID", "BaitID", "ColorInd"), all=TRUE)
Shortind_incomplete<-merge(Shortind_incomplete, Individuals[, c("NestID", "BaitID", "ColorInd", "Weight_ind")], by=c("NestID", "BaitID", "ColorInd"))
Shortpot_incomplete<-merge(Shortpot_incomplete, Individuals[, c("NestID", "BaitID", "ColorInd","Weight_ind")], by=c("NestID", "BaitID", "ColorInd"))
## Nesthoogte per vliegtijd toevoegen
Flights_incomplete<-merge(Flights_incomplete, Nests[, c("NestID", "Height")], by=c("NestID"), all=TRUE)
Shortind_incomplete<-merge(Shortind_incomplete, Nests[, c("NestID", "Height")], by=c("NestID"))
Shortpot_incomplete<-merge(Shortpot_incomplete, Nests[, c("NestID", "Height")], by=c("NestID"))
library(ggplot2)
library(ggpubr)Volgende datasets zijn gecreëerd:
- Flights_incomplete: dataset met alle vliegtijden
- Shortind_incomplete: dataset met kortste vliegtijden per individu
- Shortpot_incomplete: dataset met kortste vliegtijden per wiekpot
Voorstel: Voor het model: Flight time ~ Distance zou ik de dataset vliegtijden per individu nemen (en eventueel per wiekpot?) Omdat we hiermee de theoretische regel 1min=100m kunnen verifiëren. De imkers nemen hiervoor altijd kortste meting
Voor modellen met weerparameters, gewicht, urbanisatie: Hiervoor zou ik telkens de hele dataset gebruiken omdat elke meting van deze factoren afhangt.
Datapunten op 2km weglaten
Deze metingen zijn nogal onzeker omdat deze waarnemingen ook van een ander nest kunnen komen. Was op 2km afstand en in Melle zijn toch redelijk wat nesten gevonden. Kans dat het van een nest is dat niet gevonden werd is groot.
Als de website van Vespawatch in orde is kan ik kijken of er eventueel een nest in de buurt is gevonden.
Voorlopig gaan we verder met de dataset zonder de outliers in Melle
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionFlights2_incomplete<-Flights_incomplete %>% filter(NestID!=1)
Shortind2_incomplete<-Shortind_incomplete %>% filter(NestID!=1)
Shortpot2_incomplete<-Shortpot_incomplete %>% filter(NestID!=1)Data exploratie
1) Flight Error vs Distance
Graphs
ggplot(Flights2_incomplete, aes(x=Distance, y=FlightError)) + geom_point(color="cadetblue2") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="cadetblue") + ggtitle("All data")+ theme(plot.title = element_text(hjust = 0.5, size=10))## Warning: Removed 9 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 9 rows containing missing values (`geom_point()`).
Model Output
library(circular)##
## Attaching package: 'circular'## The following objects are masked from 'package:stats':
##
## sd, varErrorcirc<-circular(Flights2_incomplete$FlightError, type=c("angles"), units=c("degrees"), rotation=c("clock"), zero=0)
lm.circular(Errorcirc, Flights2_incomplete$Distance, type=c("c-l"), init=c(1))##
## Call:
## lm.circular.cl(y = ..1, x = ..2, init = ..3)
##
##
## Circular-Linear Regression
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## [1,] 0.3983 0.1326 3.005 0.00133 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Log-Likelihood: 420.8
##
## Summary: (mu in radians)
## mu: -167.6 ( 1.035 ) kappa: 12.72 ( 1.109 )
## p-values are approximated using normal distributionMoet ik 1 invullen bij init? =“a vector with initial values of length equal to the columns of x”
2) ForagingSpeed vs Temperature
Graphs
Grafieken zonder outliers telkens voor de volgende datasets
volledige dataset
enkel kortste vliegtijden per individu
enkel kortste vliegtijden per wiekpot
Model Output
All data
Hoogsignificant
Normality niet ok!
Indien log(ForagingSpeed) ~ log(Temperature) wel! Shapiro test (p-value=0.2979)
Indien log(ForagingSpeed) ~ Temperature wel! Shapiro test (p-value=0.1341)
model_temp_all<-lm(ForagingSpeed ~ Temperature, na.action=na.exclude, data=Flights2_incomplete)
summary(model_temp_all)##
## Call:
## lm(formula = ForagingSpeed ~ Temperature, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.8197 -0.7096 -0.2606 0.7950 3.4308
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.08514 0.31735 -3.419 0.000776 ***
## Temperature 0.19308 0.01673 11.543 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.173 on 181 degrees of freedom
## (78 observations deleted due to missingness)
## Multiple R-squared: 0.424, Adjusted R-squared: 0.4208
## F-statistic: 133.2 on 1 and 181 DF, p-value: < 2.2e-16res<-residuals(model_temp_all)
shapiro.test(res)##
## Shapiro-Wilk normality test
##
## data: res
## W = 0.973, p-value = 0.001288qqnorm(res)
qqline(res)
3) Flight time vs Distance + Temperature
Graph
library(knitr)
library(kableExtra)## Warning in !is.null(rmarkdown::metadata$output) && rmarkdown::metadata$output
## %in% : 'length(x) = 2 > 1' in coercion to 'logical(1)'##
## Attaching package: 'kableExtra'## The following object is masked from 'package:dplyr':
##
## group_rowslibrary("plot3D")
x <- Flights2_incomplete$Distance
y <- Flights2_incomplete$Temperature
z <- Flights2_incomplete$Flighttime_min
fit <- lm(z ~ x + y, na.action=na.exclude)
x.pred <- seq(min(x[!is.na(x)]), max(x[!is.na(x)]), length.out = 20)
y.pred <- seq(min(y[!is.na(y)]), max(y[!is.na(y)]), length.out = 20)
xy <- expand.grid( x = x.pred, y = y.pred)
z.pred <- matrix(predict(fit, newdata = xy),
nrow = 20, ncol = 20)
fitpoints <- predict(fit)
scatter3D(x, y, z, pch = 19, cex = 0.6, colvar=FALSE, col="dodgerblue3", theta = 210, phi = 10, bty="u", col.panel ="grey93", expand =0.4, col.grid = "white", xlab = "Distance", ylab = "Temperature", zlab = "Flight time", surf = list(x = x.pred, y = y.pred, z = z.pred,
facets = TRUE, col=ramp.col(col = c("dodgerblue4", "seagreen2"), n = 100, alpha=0.8), fit = fitpoints, border="black"),main = "Flight time vs Distance + Temperature")
Met plotly
Had met deze link problemen met expand.grid https://stackoverflow.com/questions/38331198/add-regression-plane-to-3d-scatter-plot-in-plotly
Dan maar grid dat van hierboven gebruikt, maar nu klopt er precies iets niet? Alle datapunten liggen boven het oppervlak.
library(plotly)##
## Attaching package: 'plotly'## The following object is masked from 'package:circular':
##
## wind## The following object is masked from 'package:ggplot2':
##
## last_plot## The following object is masked from 'package:stats':
##
## filter## The following object is masked from 'package:graphics':
##
## layoutlibrary(tidyverse)## ── Attaching packages
## ───────────────────────────────────────
## tidyverse 1.3.2 ──## ✔ tibble 3.1.8 ✔ purrr 1.0.1
## ✔ tidyr 1.2.1 ✔ stringr 1.5.0
## ✔ readr 2.1.4 ✔ forcats 1.0.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ plotly::filter() masks dplyr::filter(), stats::filter()
## ✖ kableExtra::group_rows() masks dplyr::group_rows()
## ✖ dplyr::lag() masks stats::lag()FlightsNoNA<-Flights2_incomplete %>% filter(Flighttime_min!="NA")
FlightsNoNA<-FlightsNoNA %>% filter(Temperature!="NA")
fig <- plot_ly(FlightsNoNA, x = ~Distance, y = ~Temperature, z = ~Flighttime_min, size=1)
fig <- fig %>% add_markers()
fig <- fig %>% layout(scene = list(xaxis = list(title = 'Distance'),
yaxis = list(title = 'Temperature'),
zaxis = list(title = 'Flight time (min)')))
p2 <- add_trace(p = fig,
z = z.pred,
x = seq(2100, 0, by = -100),
y = seq(0, 30, by = 10),
type = "surface")
p2Model Ouput
All data
Distance en temperatuur hoogsignificant
Normality niet ok!
Poisson en log/sqrt werken niet
model_tempdist_all<-lm(Flighttime_min ~ Distance + Temperature, na.action=na.exclude, data=Flights2_incomplete)
summary(model_tempdist_all)##
## Call:
## lm(formula = Flighttime_min ~ Distance + Temperature, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5147 -1.2599 -0.5980 0.6598 12.9039
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.3044798 0.6078392 8.727 1.74e-15 ***
## Distance 0.0074393 0.0008063 9.226 < 2e-16 ***
## Temperature -0.1929755 0.0356478 -5.413 1.96e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.216 on 180 degrees of freedom
## (78 observations deleted due to missingness)
## Multiple R-squared: 0.3254, Adjusted R-squared: 0.3179
## F-statistic: 43.41 on 2 and 180 DF, p-value: 4.131e-16res<-residuals(model_tempdist_all)
shapiro.test(res)##
## Shapiro-Wilk normality test
##
## data: res
## W = 0.74053, p-value < 2.2e-16qqnorm(res)
qqline(res)
4) ForagingSpeed vs Height
Graphs
plot10<-ggplot(Flights2_incomplete, aes(x=Height, y=ForagingSpeed)) + geom_point(color="burlywood3") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="chocolate4") + ggtitle("All data")+ theme(plot.title = element_text(hjust = 0.5, size=10))
plot11<-ggplot(Shortind2_incomplete, aes(x=Height, y=ForagingSpeed)) + geom_point(color="burlywood3") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="chocolate4") + ggtitle("Shortest per ind.") + theme(plot.title = element_text(hjust = 0.5, size=10))
plot12<-ggplot(Shortpot2_incomplete, aes(x=Height, y=ForagingSpeed)) + geom_point(color="burlywood3") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="chocolate4") + ggtitle("Shortest per jar")+ theme(plot.title = element_text(hjust = 0.5, size=10))
ggarrange(plot10, plot11, plot12 + rremove("x.text"),
labels = c("A", "B", "C"),
ncol = 2, nrow = 2)
Model Ouput
All data
Hoogsignificant
Normality niet ok!
Poisson en log/sqrt werken niet
model_height_all<-lm(ForagingSpeed ~ Height, na.action=na.exclude, data=Flights2_incomplete)
summary(model_height_all)##
## Call:
## lm(formula = ForagingSpeed ~ Height, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.7394 -1.1905 -0.1984 1.0376 8.3218
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.98208 0.22241 8.912 < 2e-16 ***
## Height 0.04264 0.01206 3.536 0.000495 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.508 on 221 degrees of freedom
## (38 observations deleted due to missingness)
## Multiple R-squared: 0.05355, Adjusted R-squared: 0.04926
## F-statistic: 12.5 on 1 and 221 DF, p-value: 0.0004949res<-residuals(model_height_all)
shapiro.test(res)##
## Shapiro-Wilk normality test
##
## data: res
## W = 0.93885, p-value = 4.793e-08qqnorm(res)
qqline(res)
5) Flight time vs Distance + Height
Graphs
Height = height of the nest
x <- Flights2_incomplete$Distance
y <- Flights2_incomplete$Height
z <- Flights2_incomplete$Flighttime_min
fit <- lm(z ~ x + y, na.action=na.exclude)
x.pred <- seq(min(x[!is.na(x)]), max(x[!is.na(x)]), length.out = 20)
y.pred <- seq(min(y[!is.na(y)]), max(y[!is.na(y)]), length.out = 20)
xy <- expand.grid( x = x.pred, y = y.pred)
z.pred <- matrix(predict(fit, newdata = xy),
nrow = 20, ncol = 20)
fitpoints <- predict(fit)
scatter3D(x, y, z, pch = 19, cex = 0.6, colvar=FALSE, col="dodgerblue3", theta = 40, phi = 15, bty="u", col.panel ="grey93", expand =0.4, col.grid = "white", xlab = "Distance", ylab = "Height", zlab = "Flight time", surf = list(x = x.pred, y = y.pred, z = z.pred,
facets = TRUE, col=ramp.col(col = c("dodgerblue4", "seagreen2"), n = 100, alpha=0.8), fit = fitpoints, border="black"),main = "Flight time vs Distance + Height")
Model Output
All data
model_distheight_all<-lm(Flighttime_min ~ Distance + Height , na.action=na.exclude, data=Flights2_incomplete)
summary(model_distheight_all)##
## Call:
## lm(formula = Flighttime_min ~ Distance + Height, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.8389 -1.2579 -0.7078 0.6378 13.6933
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.2142938 0.3686312 8.720 6.91e-16 ***
## Distance 0.0058864 0.0005858 10.048 < 2e-16 ***
## Height -0.0634323 0.0183671 -3.454 0.000663 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.284 on 220 degrees of freedom
## (38 observations deleted due to missingness)
## Multiple R-squared: 0.3267, Adjusted R-squared: 0.3206
## F-statistic: 53.38 on 2 and 220 DF, p-value: < 2.2e-16Height effect blijkt toch significant. In de negatieve zin weliswaar. Hoe hoger het nest hoe minder lang hij erover doet. Zou het omgekeerde verwachten..
Voorstel: Model volgens Pythagoras?
Hoogsignificant
model_distheight2_all<-lm(Flighttime_min ~ sqrt(I(Distance^2) + I(Height^2)) , na.action=na.exclude, data=Flights2_incomplete)
summary(model_distheight2_all)##
## Call:
## lm(formula = Flighttime_min ~ sqrt(I(Distance^2) + I(Height^2)),
## data = Flights2_incomplete, na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.7477 -1.2641 -0.7849 0.3824 13.8647
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.2285116 0.2429953 9.171 <2e-16 ***
## sqrt(I(Distance^2) + I(Height^2)) 0.0056853 0.0005979 9.508 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.339 on 221 degrees of freedom
## (38 observations deleted due to missingness)
## Multiple R-squared: 0.2903, Adjusted R-squared: 0.2871
## F-statistic: 90.41 on 1 and 221 DF, p-value: < 2.2e-166) ForagingSpeed vs Cloudcoverage
Graphs
plot13<-ggplot(Flights2_incomplete, aes(x=Cloudcoverage, y=ForagingSpeed)) + geom_point(color="lightblue") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="darkblue") + ggtitle("All data")+ theme(plot.title = element_text(hjust = 0.5, size=10))
plot14<-ggplot(Shortind2_incomplete, aes(x=Cloudcoverage, y=ForagingSpeed)) + geom_point(color="lightblue") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="darkblue") + ggtitle("Shortest per ind.") + theme(plot.title = element_text(hjust = 0.5, size=10))
plot15<-ggplot(Shortpot2_incomplete, aes(x=Cloudcoverage, y=ForagingSpeed)) + geom_point(color="lightblue") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="darkblue") + ggtitle("Shortest per jar")+ theme(plot.title = element_text(hjust = 0.5, size=10))
ggarrange(plot13, plot14, plot15 + rremove("x.text"),
labels = c("A", "B", "C"),
ncol = 2, nrow = 2)
Model Ouput
All data
Hoogsignificant
Normality niet ok!
Poisson en log/sqrt werken niet
model_cloud_all<-lm(ForagingSpeed ~ Cloudcoverage, na.action=na.exclude, data=Flights2_incomplete)
summary(model_cloud_all)##
## Call:
## lm(formula = ForagingSpeed ~ Cloudcoverage, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1845 -1.2324 -0.3021 1.1390 3.8835
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.5341 0.1966 12.888 <2e-16 ***
## Cloudcoverage -0.5491 0.3208 -1.711 0.0891 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.491 on 150 degrees of freedom
## (109 observations deleted due to missingness)
## Multiple R-squared: 0.01915, Adjusted R-squared: 0.01261
## F-statistic: 2.929 on 1 and 150 DF, p-value: 0.08906res<-residuals(model_cloud_all)
shapiro.test(res)##
## Shapiro-Wilk normality test
##
## data: res
## W = 0.94063, p-value = 5.166e-06qqnorm(res)
qqline(res)
7) ForagingSpeed vs Weight individual
Graphs
plot16<-ggplot(Flights2_incomplete, aes(x=Weight_ind, y=ForagingSpeed)) + geom_point(color="plum") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="darkorchid4") + ggtitle("All data")+ theme(plot.title = element_text(hjust = 0.5, size=10))
plot17<-ggplot(Shortind2_incomplete, aes(x=Weight_ind, y=ForagingSpeed)) + geom_point(color="plum") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="darkorchid4") + ggtitle("Shortest per ind.") + theme(plot.title = element_text(hjust = 0.5, size=10))
plot18<-ggplot(Shortpot2_incomplete, aes(x=Weight_ind, y=ForagingSpeed)) + geom_point(color="plum") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="darkorchid4") + ggtitle("Shortest per jar")+ theme(plot.title = element_text(hjust = 0.5, size=10))
ggarrange(plot16, plot17, plot18 + rremove("x.text"),
labels = c("A", "B", "C"),
ncol = 2, nrow = 2)
Model Output
All data
Niet significant
Normality niet ok!
sqrt(ForagingSpeed) ~ sqrt(Weight_ind) met Poisson nipt wel. Shapiro test (p-value=0.06463)
model_weight_all<-lm(ForagingSpeed ~ Weight_ind, na.action=na.exclude, data=Flights2_incomplete)
summary(model_weight_all)##
## Call:
## lm(formula = ForagingSpeed ~ Weight_ind, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.8995 -0.9467 -0.2375 1.0092 2.5308
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.5517 0.5969 4.275 4.88e-05 ***
## Weight_ind -1.0014 1.7162 -0.583 0.561
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.117 on 87 degrees of freedom
## (172 observations deleted due to missingness)
## Multiple R-squared: 0.003898, Adjusted R-squared: -0.007551
## F-statistic: 0.3405 on 1 and 87 DF, p-value: 0.5611res<-residuals(model_weight_all)
shapiro.test(res)##
## Shapiro-Wilk normality test
##
## data: res
## W = 0.94628, p-value = 0.001071qqnorm(res)
qqline(res)
8.1) ForagingSpeed vs Windspeed
Graphs
Telkens voor de modellen
ForagingSpeed ~ Windspeed
ForagingSpeed ~ Windspeed²
plot19<-ggplot(Flights2_incomplete, aes(x=Windspeed, y=ForagingSpeed)) + geom_point(color="khaki3") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="olivedrab") + ggtitle("All data")+ theme(plot.title = element_text(hjust = 0.5, size=10))
plot20<-ggplot(Shortind_incomplete, aes(x=Windspeed, y=ForagingSpeed)) + geom_point(color="khaki3") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="olivedrab") + ggtitle("Shortest per ind.") + theme(plot.title = element_text(hjust = 0.5, size=10))
plot21<-ggplot(Shortpot_incomplete, aes(x=Windspeed, y=ForagingSpeed)) + geom_point(color="khaki3") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="olivedrab") + ggtitle("Shortest per jar")+ theme(plot.title = element_text(hjust = 0.5, size=10))
plot22<-ggplot(Flights2_incomplete, aes(x=Windspeed, y=ForagingSpeed)) + geom_point(color="khaki3") + geom_smooth(method="lm", formula =y ~ I(x^2), se=TRUE, fullrange=FALSE, level=0.95, color="olivedrab") + ggtitle("All data")+ theme(plot.title = element_text(hjust = 0.5, size=10))
plot23<-ggplot(Shortind_incomplete, aes(x=Windspeed, y=ForagingSpeed)) + geom_point(color="khaki3") + geom_smooth(method="lm", formula =y ~ I(x^2), se=TRUE, fullrange=FALSE, level=0.95, color="olivedrab") + ggtitle("Shortest per ind.") + theme(plot.title = element_text(hjust = 0.5, size=10))
plot24<-ggplot(Shortpot_incomplete, aes(x=Windspeed, y=ForagingSpeed)) + geom_point(color="khaki3") + geom_smooth(method="lm", formula =y ~ I(x^2), se=TRUE, fullrange=FALSE, level=0.95, color="olivedrab") + ggtitle("Shortest per jar")+ theme(plot.title = element_text(hjust = 0.5, size=10))
ggarrange(plot19, plot20, plot21, plot22, plot23, plot24 + rremove("x.text"),
labels = c("A", "B", "C"),
ncol = 3, nrow = 2)
Model Output
All data Beide modellen significant
Normality niet ok!
Poisson en log/sqrt werken niet
model_wind_all<-lm(ForagingSpeed ~ Windspeed, na.action=na.exclude, data=Flights2_incomplete)
summary(model_wind_all)##
## Call:
## lm(formula = ForagingSpeed ~ Windspeed, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.772 -1.127 -0.292 1.009 4.390
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.2272 0.2644 12.204 < 2e-16 ***
## Windspeed -0.3667 0.1129 -3.249 0.00139 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.514 on 172 degrees of freedom
## (87 observations deleted due to missingness)
## Multiple R-squared: 0.05783, Adjusted R-squared: 0.05236
## F-statistic: 10.56 on 1 and 172 DF, p-value: 0.001392model_wind2_all<-lm(ForagingSpeed ~ I(Windspeed^2), na.action=na.exclude, data=Flights2_incomplete)
summary(model_wind2_all)##
## Call:
## lm(formula = ForagingSpeed ~ I(Windspeed^2), data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4834 -1.1718 -0.2343 1.0190 4.3176
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.86827 0.17828 16.089 < 2e-16 ***
## I(Windspeed^2) -0.07563 0.02479 -3.051 0.00265 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.519 on 172 degrees of freedom
## (87 observations deleted due to missingness)
## Multiple R-squared: 0.05133, Adjusted R-squared: 0.04581
## F-statistic: 9.306 on 1 and 172 DF, p-value: 0.002646res<-residuals(model_wind_all)
shapiro.test(res)##
## Shapiro-Wilk normality test
##
## data: res
## W = 0.96386, p-value = 0.0001765qqnorm(res)
qqline(res)
res<-residuals(model_wind2_all)
shapiro.test(res)##
## Shapiro-Wilk normality test
##
## data: res
## W = 0.96413, p-value = 0.0001883qqnorm(res)
qqline(res)
8.2) ForagingSpeed vs Windspeed | afhankelijk van de windrichting
Hiervoor werd telkens voor elke meting nagegaan of de hoornaar met meewind (tailwind), tegenwind (upwind) of loodrechte wind (perpendicular) te maken had. Dit volgens de formules:
|𝜃flight −𝜃wind| ≤ 45 is tailwind
45 < |𝜃flight −𝜃wind|<135 is (quasi) perpendicular
|𝜃 flight −𝜃wind| ≥135 upwind
Voorstel Misschien kan ik tegenwind en meewind samenvoegen aangezien de hoornaar telkens heen en terug vliegt?
Graphs
ggplot(data=subset(Flights2_incomplete, !is.na(Wind)), aes(x= Wind, col=Wind, y=ForagingSpeed)) + geom_boxplot()## Warning: Removed 6 rows containing non-finite values (`stat_boxplot()`).
ggplot(data=subset(Flights2_incomplete, !is.na(Wind)), aes(x= Windspeed, col=Wind, y=ForagingSpeed)) + geom_point() + facet_grid(~Wind) + geom_smooth(method="lm", formula = y ~ I(x^2), se=TRUE, fullrange=FALSE, level=0.95)## Warning: Removed 6 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 6 rows containing missing values (`geom_point()`).
Model Output
Taiwind licht significant
Upwind significant, maar zeer lage R²
data_tailwind<-Flights2_incomplete %>% filter(Wind!="tailwind")
data_perpendicular<-Flights2_incomplete %>% filter(Wind!="perpendicular")
data_upwind<-Flights2_incomplete %>% filter(Wind!="upwind")
model_tailwind<-lm(ForagingSpeed ~ I(Windspeed^2), na.action=na.exclude, data=data_tailwind)
summary(model_tailwind)##
## Call:
## lm(formula = ForagingSpeed ~ I(Windspeed^2), data = data_tailwind,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.2414 -1.1136 -0.3614 0.9290 4.5141
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.62575 0.20359 12.897 <2e-16 ***
## I(Windspeed^2) -0.06413 0.02670 -2.401 0.0177 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.539 on 138 degrees of freedom
## (4 observations deleted due to missingness)
## Multiple R-squared: 0.04011, Adjusted R-squared: 0.03315
## F-statistic: 5.766 on 1 and 138 DF, p-value: 0.01767model_perpendicular<-lm(ForagingSpeed ~ I(Windspeed^2), na.action=na.exclude, data=data_perpendicular)
summary(model_perpendicular)##
## Call:
## lm(formula = ForagingSpeed ~ I(Windspeed^2), data = data_perpendicular,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1745 -1.3644 -0.2466 1.1510 4.5741
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.22570 0.34457 6.459 2.89e-08 ***
## I(Windspeed^2) 0.02088 0.05736 0.364 0.717
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.679 on 55 degrees of freedom
## (4 observations deleted due to missingness)
## Multiple R-squared: 0.002404, Adjusted R-squared: -0.01573
## F-statistic: 0.1325 on 1 and 55 DF, p-value: 0.7172model_upwind<-lm(ForagingSpeed ~ I(Windspeed^2), na.action=na.exclude, data=data_upwind)
summary(model_upwind)##
## Call:
## lm(formula = ForagingSpeed ~ I(Windspeed^2), data = data_upwind,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6756 -1.1091 -0.1986 0.9393 3.5654
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.06119 0.19631 15.594 < 2e-16 ***
## I(Windspeed^2) -0.09290 0.02585 -3.594 0.000469 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.365 on 123 degrees of freedom
## (4 observations deleted due to missingness)
## Multiple R-squared: 0.09504, Adjusted R-squared: 0.08769
## F-statistic: 12.92 on 1 and 123 DF, p-value: 0.00046929) Flight error vs urbanisation (25m, 50m, 100m)
Flight error is the difference between the actual angle from the bait to the nest and the flight direction I measured.
Urbanisatiecirkels
Graphs
plot25<-ggplot(data=Flights2_incomplete, aes(x=Urbanisation25m, y=FlightError)) + geom_point() + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95) + ggtitle("Urbanisation circles 25m")+ theme(plot.title = element_text(hjust = 0.5, size=10))
plot26<-ggplot(data=Flights2_incomplete, aes(x=Urbanisation50m, y=FlightError)) + geom_point()+ geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95) + ggtitle("Urbanisation circles 50m")+ theme(plot.title = element_text(hjust = 0.5, size=10))
plot27<-ggplot(data=Flights2_incomplete, aes(x=Urbanisation100m, y=FlightError)) + geom_point()+ geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95) + ggtitle("Urbanisation circles 100m")+ theme(plot.title = element_text(hjust = 0.5, size=10))
ggarrange(plot25, plot26, plot27 + rremove("x.text"),
labels = c("A", "B", "C"),
ncol = 2, nrow = 2)## Warning: Removed 9 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 9 rows containing missing values (`geom_point()`).## Warning: Removed 9 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 9 rows containing missing values (`geom_point()`).## Warning: Removed 9 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 9 rows containing missing values (`geom_point()`).
Model Output
library(circular)
Errorcirc<-circular(Flights2_incomplete$FlightError, type=c("angles"), units=c("degrees"), rotation=c("clock"), zero=0)
lm.circular(Errorcirc, Flights2_incomplete$Urbanisation25m, type=c("c-l"), init=c(1))##
## Call:
## lm.circular.cl(y = ..1, x = ..2, init = ..3)
##
##
## Circular-Linear Regression
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## [1,] 0.02084 0.03946 0.528 0.299
##
## Log-Likelihood: 418.9
##
## Summary: (mu in radians)
## mu: 14.89 ( 1.043 ) kappa: 12.54 ( 1.093 )
## p-values are approximated using normal distributionMoet ik 1 invullen bij init? “a vector with initial values of length equal to the columns of x”
lm.circular(Errorcirc, Flights2_incomplete$Urbanisation50m, type=c("c-l"), init=c(1))##
## Call:
## lm.circular.cl(y = ..1, x = ..2, init = ..3)
##
##
## Circular-Linear Regression
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## [1,] 0.03933 0.03923 1.002 0.158
##
## Log-Likelihood: 419
##
## Summary: (mu in radians)
## mu: 15.3 ( 1.042 ) kappa: 12.56 ( 1.094 )
## p-values are approximated using normal distributionNiet significant
lm.circular(Errorcirc, Flights2_incomplete$Urbanisation100m, type=c("c-l"), init=c(1))##
## Call:
## lm.circular.cl(y = ..1, x = ..2, init = ..3)
##
##
## Circular-Linear Regression
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## [1,] 0.14864 0.03812 3.899 4.82e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Log-Likelihood: 421.3
##
## Summary: (mu in radians)
## mu: 17.8 ( 1.033 ) kappa: 12.77 ( 1.113 )
## p-values are approximated using normal distributionSignificant
Urbanisatietrajecten
Graphs
plot28<-ggplot(data=subset(Flights2_incomplete, !is.na(Observer)), aes(x=Traject25m, y=FlightError)) + geom_point(col="hotpink1") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="violetred4")
plot29<-ggplot(data=subset(Flights2_incomplete, !is.na(Observer)), aes(x=Traject50m, y=FlightError)) + geom_point(col="hotpink1") + geom_smooth(method="lm", formula =y ~ x , se=TRUE, fullrange=FALSE, level=0.95, color="violetred4")
plot30<-ggplot(data=subset(Flights2_incomplete, !is.na(Observer)), aes(x=Traject100m, y=FlightError)) + geom_point(col="hotpink1")+ geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="violetred4")
ggarrange(plot28, plot29, plot30 + rremove("x.text"),
labels = c("A", "B", "C"),
ncol = 2, nrow = 2)## Warning: Removed 9 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 9 rows containing missing values (`geom_point()`).## Warning: Removed 9 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 9 rows containing missing values (`geom_point()`).## Warning: Removed 9 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 9 rows containing missing values (`geom_point()`).
Model Output
Traject25m, Traject50m en Traject100m significant
library(circular)
Errorcirc<-circular(Flights2_incomplete$FlightError, type=c("angles"), units=c("degrees"), rotation=c("clock"), zero=0)
lm.circular(Errorcirc, Flights2_incomplete$Traject25m, type=c("c-l"), init=c(1))##
## Call:
## lm.circular.cl(y = ..1, x = ..2, init = ..3)
##
##
## Circular-Linear Regression
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## [1,] 0.16459 0.03502 4.7 1.3e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Log-Likelihood: 423
##
## Summary: (mu in radians)
## mu: 18.32 ( 1.026 ) kappa: 12.94 ( 1.128 )
## p-values are approximated using normal distributionlm.circular(Errorcirc, Flights2_incomplete$Traject50m, type=c("c-l"), init=c(1))##
## Call:
## lm.circular.cl(y = ..1, x = ..2, init = ..3)
##
##
## Circular-Linear Regression
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## [1,] 0.1231 0.0357 3.448 0.000282 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Log-Likelihood: 420.9
##
## Summary: (mu in radians)
## mu: 17.4 ( 1.035 ) kappa: 12.73 ( 1.11 )
## p-values are approximated using normal distributionlm.circular(Errorcirc, Flights2_incomplete$Traject100m, type=c("c-l"), init=c(1))##
## Call:
## lm.circular.cl(y = ..1, x = ..2, init = ..3)
##
##
## Circular-Linear Regression
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## [1,] 0.15022 0.03505 4.286 9.11e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Log-Likelihood: 421.6
##
## Summary: (mu in radians)
## mu: 18.19 ( 1.031 ) kappa: 12.81 ( 1.116 )
## p-values are approximated using normal distributionSignificant
10) ForagingSpeed vs Urbanisation
Graphs
Urbanisatiecirkels niet berekend, meteen trajecten genomen want die zijn betere maatstaf
Alle data
plot31<-ggplot(data=subset(Flights2_incomplete, !is.na(Observer)), aes(x=Traject25m, y=ForagingSpeed)) + geom_point(col="slateblue1") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="slateblue4")
plot32<-ggplot(data=subset(Flights2_incomplete, !is.na(Observer)), aes(x=Traject50m, y=ForagingSpeed)) + geom_point(col="slateblue1") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="slateblue4")
plot33<-ggplot(data=subset(Flights2_incomplete, !is.na(Observer)), aes(x=Traject100m, y=ForagingSpeed)) + geom_point(col="slateblue1") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="slateblue4")
ggarrange(plot31, plot32, plot33 + rremove("x.text"),
labels = c("A", "B", "C"),
ncol = 2, nrow = 2)## Warning: Removed 26 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 26 rows containing missing values (`geom_point()`).## Warning: Removed 26 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 26 rows containing missing values (`geom_point()`).## Warning: Removed 26 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 26 rows containing missing values (`geom_point()`).
Shortest per individual
plot34<-ggplot(data=subset(Shortind_incomplete, !is.na(Observer)), aes(x=Traject25m, y=ForagingSpeed)) + geom_point(col="lemonchiffon3") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="lemonchiffon4")
plot35<-ggplot(data=subset(Shortind_incomplete, !is.na(Observer)), aes(x=Traject50m, y=ForagingSpeed)) + geom_point(col="lemonchiffon3") +
geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="lemonchiffon4")
plot36<-ggplot(data=subset(Shortind_incomplete, !is.na(Observer)), aes(x=Traject100m, y=ForagingSpeed)) + geom_point(col="lemonchiffon3") + geom_smooth(method="lm", formula =y ~ x, se=TRUE, fullrange=FALSE, level=0.95, color="lemonchiffon4")
ggarrange(plot34, plot35, plot36 + rremove("x.text"),
labels = c("A", "B", "C"),
ncol = 2, nrow = 2)
Model Output
All data All significant
Normality not ok!
met Poisson wel normaal! Shapiro-test p-value= 0.3992
model_urb25_all<-lm(ForagingSpeed ~ Traject25m, na.action=na.exclude, data=Flights2_incomplete)
summary(model_urb25_all)##
## Call:
## lm(formula = ForagingSpeed ~ Traject25m, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.4703 -0.7871 -0.0828 0.7738 6.6260
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.6910 0.1379 26.76 <2e-16 ***
## Traject25m -5.5106 0.5340 -10.32 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.318 on 233 degrees of freedom
## (26 observations deleted due to missingness)
## Multiple R-squared: 0.3137, Adjusted R-squared: 0.3107
## F-statistic: 106.5 on 1 and 233 DF, p-value: < 2.2e-16model_urb50_all<-lm(ForagingSpeed ~ Traject50m, na.action=na.exclude, data=Flights2_incomplete)
summary(model_urb50_all)##
## Call:
## lm(formula = ForagingSpeed ~ Traject50m, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.0798 -0.7869 -0.0795 0.8003 6.5421
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.8511 0.1420 27.12 <2e-16 ***
## Traject50m -6.1889 0.5569 -11.11 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.286 on 233 degrees of freedom
## (26 observations deleted due to missingness)
## Multiple R-squared: 0.3464, Adjusted R-squared: 0.3436
## F-statistic: 123.5 on 1 and 233 DF, p-value: < 2.2e-16model_urb100_all<-lm(ForagingSpeed ~ Traject100m, na.action=na.exclude, data=Flights2_incomplete)
summary(model_urb100_all)##
## Call:
## lm(formula = ForagingSpeed ~ Traject100m, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9544 -0.8053 -0.1753 0.8174 6.4851
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.9952 0.1497 26.69 <2e-16 ***
## Traject100m -6.5645 0.5765 -11.39 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.275 on 233 degrees of freedom
## (26 observations deleted due to missingness)
## Multiple R-squared: 0.3575, Adjusted R-squared: 0.3548
## F-statistic: 129.7 on 1 and 233 DF, p-value: < 2.2e-16#Residuals voor Traject100m
res<-residuals(model_urb100_all)
shapiro.test(res)##
## Shapiro-Wilk normality test
##
## data: res
## W = 0.9675, p-value = 3.322e-05qqnorm(res)
qqline(res)
Shortest per individual
Allemaal significant
model_urb25_ind<-lm(ForagingSpeed ~ Traject25m, na.action=na.exclude, data=Shortind_incomplete)
summary(model_urb25_ind)##
## Call:
## lm(formula = ForagingSpeed ~ Traject25m, data = Shortind_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.8480 -0.9978 0.0167 0.7126 6.2478
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.0691 0.2213 18.383 <2e-16 ***
## Traject25m -4.3231 1.2337 -3.504 7e-04 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.549 on 95 degrees of freedom
## Multiple R-squared: 0.1145, Adjusted R-squared: 0.1051
## F-statistic: 12.28 on 1 and 95 DF, p-value: 0.0007002model_urb50_ind<-lm(ForagingSpeed ~ Traject50m, na.action=na.exclude, data=Shortind_incomplete)
summary(model_urb50_ind)##
## Call:
## lm(formula = ForagingSpeed ~ Traject50m, data = Shortind_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.5064 -0.9661 -0.0851 0.6831 6.1960
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.1832 0.2272 18.415 < 2e-16 ***
## Traject50m -5.0598 1.2748 -3.969 0.00014 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.524 on 95 degrees of freedom
## Multiple R-squared: 0.1422, Adjusted R-squared: 0.1332
## F-statistic: 15.75 on 1 and 95 DF, p-value: 0.0001401model_urb100_ind<-lm(ForagingSpeed ~ Traject100m, na.action=na.exclude, data=Shortind_incomplete)
summary(model_urb100_ind)##
## Call:
## lm(formula = ForagingSpeed ~ Traject100m, data = Shortind_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3694 -0.9967 -0.0850 0.7380 6.2148
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.2295 0.2358 17.933 < 2e-16 ***
## Traject100m -5.1207 1.2901 -3.969 0.00014 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.524 on 95 degrees of freedom
## Multiple R-squared: 0.1422, Adjusted R-squared: 0.1332
## F-statistic: 15.75 on 1 and 95 DF, p-value: 0.000140111) ForagingSpeed vs Temperatuur + Urbanisation
Aangezien temperatuur en urbanisatie de beste predictoren zijn kunnen we ze eens samen in een model steken.
x <- Flights2_incomplete$Temperature
y <- Flights2_incomplete$Traject100m
z <- Flights2_incomplete$ForagingSpeed
fit <- lm(z ~ x + y, na.action=na.exclude)
x.pred <- seq(min(x[!is.na(x)]), max(x[!is.na(x)]), length.out = 20)
y.pred <- seq(min(y[!is.na(y)]), max(y[!is.na(y)]), length.out = 20)
xy <- expand.grid( x = x.pred, y = y.pred)
z.pred <- matrix(predict(fit, newdata = xy),
nrow = 20, ncol = 20)
fitpoints <- predict(fit)
scatter3D(x, y, z, pch = 19, cex = 0.6, colvar=FALSE, col="dodgerblue3", theta = 210, phi = 10, bty="u", col.panel ="grey93", expand =0.4, col.grid = "white", xlab = "Temperature", ylab = "Urbanisation (Traject100m)", zlab = "Flight Speed", surf = list(x = x.pred, y = y.pred, z = z.pred,
facets = TRUE, col=ramp.col(col = c("dodgerblue4", "seagreen2"), n = 100, alpha=0.8), fit = fitpoints, border="black"),main = "Flight Speed vs Temperature + Urbanisation")
Allemaal significant! Traject 100m hoogste R²: 0.4914
model_4_all<-lm(ForagingSpeed ~ Temperature + Traject25m, na.action=na.exclude, data=Flights2_incomplete)
summary(model_4_all)##
## Call:
## lm(formula = ForagingSpeed ~ Temperature + Traject25m, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.8161 -0.6685 -0.0619 0.6084 3.1989
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.13598 0.63594 1.786 0.0757 .
## Temperature 0.11423 0.02551 4.477 1.34e-05 ***
## Traject25m -3.27294 0.82221 -3.981 9.96e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.127 on 180 degrees of freedom
## (78 observations deleted due to missingness)
## Multiple R-squared: 0.4706, Adjusted R-squared: 0.4647
## F-statistic: 80.01 on 2 and 180 DF, p-value: < 2.2e-16model_5_all<-lm(ForagingSpeed ~ Temperature + Traject50m, na.action=na.exclude, data=Flights2_incomplete)
summary(model_5_all)##
## Call:
## lm(formula = ForagingSpeed ~ Temperature + Traject50m, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9005 -0.6330 -0.0565 0.6201 3.1846
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.49113 0.63681 2.342 0.0203 *
## Temperature 0.10421 0.02503 4.163 4.86e-05 ***
## Traject50m -3.96756 0.86416 -4.591 8.25e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.113 on 180 degrees of freedom
## (78 observations deleted due to missingness)
## Multiple R-squared: 0.4844, Adjusted R-squared: 0.4787
## F-statistic: 84.55 on 2 and 180 DF, p-value: < 2.2e-16model_6_all<-lm(ForagingSpeed ~ Temperature + Traject100m, na.action=na.exclude, data=Flights2_incomplete)
summary(model_6_all)##
## Call:
## lm(formula = ForagingSpeed ~ Temperature + Traject100m, data = Flights2_incomplete,
## na.action = na.exclude)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.94370 -0.63064 -0.09026 0.65454 3.11185
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.88673 0.65334 2.888 0.004355 **
## Temperature 0.09470 0.02483 3.814 0.000188 ***
## Traject100m -4.67106 0.91432 -5.109 8.22e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.099 on 180 degrees of freedom
## (78 observations deleted due to missingness)
## Multiple R-squared: 0.497, Adjusted R-squared: 0.4914
## F-statistic: 88.91 on 2 and 180 DF, p-value: < 2.2e-16Varpart
library(vegan) varpart(Flights2_incomplete$Flighttime_min, ~Distance, ~Temperatuur, ~Windspeed, na.action=na.exclude, data= Flights2_incomplete) Probleem met NA
TO DO - circulaire statistiek verder uitwerken ?
Statistische modellen probeersels
# Model kiezen
library(car)## Loading required package: carData##
## Attaching package: 'car'## The following object is masked from 'package:purrr':
##
## some## The following object is masked from 'package:dplyr':
##
## recodelibrary(carData)
library(leaps)
select1<-regsubsets(ForagingSpeed ~ Temperature + Cloudcoverage + I(Windspeed^2) + Weight_ind + Traject100m, na.action=na.exclude, data=Flights2_incomplete, nbest=3)
summary(select1)## Subset selection object
## Call: regsubsets.formula(ForagingSpeed ~ Temperature + Cloudcoverage +
## I(Windspeed^2) + Weight_ind + Traject100m, na.action = na.exclude,
## data = Flights2_incomplete, nbest = 3)
## 5 Variables (and intercept)
## Forced in Forced out
## Temperature FALSE FALSE
## Cloudcoverage FALSE FALSE
## I(Windspeed^2) FALSE FALSE
## Weight_ind FALSE FALSE
## Traject100m FALSE FALSE
## 3 subsets of each size up to 5
## Selection Algorithm: exhaustive
## Temperature Cloudcoverage I(Windspeed^2) Weight_ind Traject100m
## 1 ( 1 ) " " " " " " " " "*"
## 1 ( 2 ) "*" " " " " " " " "
## 1 ( 3 ) " " " " "*" " " " "
## 2 ( 1 ) " " "*" " " " " "*"
## 2 ( 2 ) "*" "*" " " " " " "
## 2 ( 3 ) " " " " " " "*" "*"
## 3 ( 1 ) "*" "*" " " " " "*"
## 3 ( 2 ) " " "*" "*" " " "*"
## 3 ( 3 ) " " "*" " " "*" "*"
## 4 ( 1 ) "*" "*" " " "*" "*"
## 4 ( 2 ) "*" "*" "*" " " "*"
## 4 ( 3 ) " " "*" "*" "*" "*"
## 5 ( 1 ) "*" "*" "*" "*" "*"plot(select1, scale="adjr2")
select2<-regsubsets(ForagingSpeed ~ Temperature + Cloudcoverage + Windspeed + Weight_ind + Traject100m +
Traject100m*Temperature + Traject100m*Cloudcoverage + Traject100m*Windspeed + Traject100m*Weight_ind + Temperature*Cloudcoverage + Temperature*Windspeed + Temperature*Weight_ind + Cloudcoverage*Windspeed + Cloudcoverage*Weight_ind + Windspeed*Weight_ind, na.action=na.exclude, data=Flights2_incomplete, nbest=3)
summary(select2)## Subset selection object
## Call: regsubsets.formula(ForagingSpeed ~ Temperature + Cloudcoverage +
## Windspeed + Weight_ind + Traject100m + Traject100m * Temperature +
## Traject100m * Cloudcoverage + Traject100m * Windspeed + Traject100m *
## Weight_ind + Temperature * Cloudcoverage + Temperature *
## Windspeed + Temperature * Weight_ind + Cloudcoverage * Windspeed +
## Cloudcoverage * Weight_ind + Windspeed * Weight_ind, na.action = na.exclude,
## data = Flights2_incomplete, nbest = 3)
## 15 Variables (and intercept)
## Forced in Forced out
## Temperature FALSE FALSE
## Cloudcoverage FALSE FALSE
## Windspeed FALSE FALSE
## Weight_ind FALSE FALSE
## Traject100m FALSE FALSE
## Temperature:Traject100m FALSE FALSE
## Cloudcoverage:Traject100m FALSE FALSE
## Windspeed:Traject100m FALSE FALSE
## Weight_ind:Traject100m FALSE FALSE
## Temperature:Cloudcoverage FALSE FALSE
## Temperature:Windspeed FALSE FALSE
## Temperature:Weight_ind FALSE FALSE
## Cloudcoverage:Windspeed FALSE FALSE
## Cloudcoverage:Weight_ind FALSE FALSE
## Windspeed:Weight_ind FALSE FALSE
## 3 subsets of each size up to 8
## Selection Algorithm: exhaustive
## Temperature Cloudcoverage Windspeed Weight_ind Traject100m
## 1 ( 1 ) " " " " " " " " "*"
## 1 ( 2 ) " " " " " " " " " "
## 1 ( 3 ) "*" " " " " " " " "
## 2 ( 1 ) " " " " " " " " "*"
## 2 ( 2 ) " " "*" " " " " "*"
## 2 ( 3 ) " " " " " " " " "*"
## 3 ( 1 ) " " " " " " " " "*"
## 3 ( 2 ) " " " " " " " " "*"
## 3 ( 3 ) " " " " " " " " "*"
## 4 ( 1 ) " " " " "*" " " "*"
## 4 ( 2 ) " " " " "*" " " "*"
## 4 ( 3 ) " " "*" "*" " " "*"
## 5 ( 1 ) " " " " " " " " "*"
## 5 ( 2 ) "*" " " " " " " "*"
## 5 ( 3 ) " " " " " " " " "*"
## 6 ( 1 ) " " " " " " " " "*"
## 6 ( 2 ) " " " " " " " " "*"
## 6 ( 3 ) " " " " " " "*" "*"
## 7 ( 1 ) " " "*" " " " " "*"
## 7 ( 2 ) " " "*" " " " " "*"
## 7 ( 3 ) " " "*" " " " " "*"
## 8 ( 1 ) "*" " " "*" "*" " "
## 8 ( 2 ) " " "*" " " " " "*"
## 8 ( 3 ) " " "*" " " " " "*"
## Temperature:Traject100m Cloudcoverage:Traject100m
## 1 ( 1 ) " " " "
## 1 ( 2 ) " " " "
## 1 ( 3 ) " " " "
## 2 ( 1 ) " " " "
## 2 ( 2 ) " " " "
## 2 ( 3 ) " " " "
## 3 ( 1 ) " " " "
## 3 ( 2 ) " " " "
## 3 ( 3 ) " " " "
## 4 ( 1 ) " " " "
## 4 ( 2 ) " " " "
## 4 ( 3 ) " " " "
## 5 ( 1 ) "*" " "
## 5 ( 2 ) " " " "
## 5 ( 3 ) "*" " "
## 6 ( 1 ) "*" " "
## 6 ( 2 ) "*" " "
## 6 ( 3 ) "*" " "
## 7 ( 1 ) "*" "*"
## 7 ( 2 ) "*" " "
## 7 ( 3 ) " " " "
## 8 ( 1 ) " " " "
## 8 ( 2 ) "*" "*"
## 8 ( 3 ) " " " "
## Windspeed:Traject100m Weight_ind:Traject100m Temperature:Cloudcoverage
## 1 ( 1 ) " " " " " "
## 1 ( 2 ) " " "*" " "
## 1 ( 3 ) " " " " " "
## 2 ( 1 ) " " " " "*"
## 2 ( 2 ) " " " " " "
## 2 ( 3 ) " " " " " "
## 3 ( 1 ) " " " " "*"
## 3 ( 2 ) " " " " "*"
## 3 ( 3 ) " " " " " "
## 4 ( 1 ) "*" " " " "
## 4 ( 2 ) "*" " " "*"
## 4 ( 3 ) "*" " " " "
## 5 ( 1 ) "*" " " "*"
## 5 ( 2 ) "*" " " "*"
## 5 ( 3 ) "*" " " " "
## 6 ( 1 ) "*" " " "*"
## 6 ( 2 ) "*" " " "*"
## 6 ( 3 ) "*" " " "*"
## 7 ( 1 ) "*" " " "*"
## 7 ( 2 ) "*" " " "*"
## 7 ( 3 ) "*" "*" "*"
## 8 ( 1 ) " " "*" "*"
## 8 ( 2 ) "*" " " "*"
## 8 ( 3 ) "*" "*" "*"
## Temperature:Windspeed Temperature:Weight_ind Cloudcoverage:Windspeed
## 1 ( 1 ) " " " " " "
## 1 ( 2 ) " " " " " "
## 1 ( 3 ) " " " " " "
## 2 ( 1 ) " " " " " "
## 2 ( 2 ) " " " " " "
## 2 ( 3 ) " " " " " "
## 3 ( 1 ) "*" " " " "
## 3 ( 2 ) " " " " "*"
## 3 ( 3 ) " " "*" " "
## 4 ( 1 ) " " " " " "
## 4 ( 2 ) " " " " " "
## 4 ( 3 ) " " " " " "
## 5 ( 1 ) "*" " " " "
## 5 ( 2 ) "*" " " " "
## 5 ( 3 ) "*" " " " "
## 6 ( 1 ) "*" " " "*"
## 6 ( 2 ) "*" "*" " "
## 6 ( 3 ) "*" " " " "
## 7 ( 1 ) "*" " " " "
## 7 ( 2 ) "*" " " "*"
## 7 ( 3 ) " " " " "*"
## 8 ( 1 ) "*" "*" " "
## 8 ( 2 ) "*" " " "*"
## 8 ( 3 ) "*" " " "*"
## Cloudcoverage:Weight_ind Windspeed:Weight_ind
## 1 ( 1 ) " " " "
## 1 ( 2 ) " " " "
## 1 ( 3 ) " " " "
## 2 ( 1 ) " " " "
## 2 ( 2 ) " " " "
## 2 ( 3 ) "*" " "
## 3 ( 1 ) " " " "
## 3 ( 2 ) " " " "
## 3 ( 3 ) "*" " "
## 4 ( 1 ) "*" " "
## 4 ( 2 ) " " " "
## 4 ( 3 ) " " " "
## 5 ( 1 ) " " " "
## 5 ( 2 ) " " " "
## 5 ( 3 ) "*" " "
## 6 ( 1 ) " " " "
## 6 ( 2 ) " " " "
## 6 ( 3 ) " " " "
## 7 ( 1 ) " " " "
## 7 ( 2 ) " " " "
## 7 ( 3 ) " " "*"
## 8 ( 1 ) " " "*"
## 8 ( 2 ) " " " "
## 8 ( 3 ) " " "*"plot(select2, scale="adjr2")
Multicollinearity check
library(ggcorrplot)
library(car)
datacor<-Flights2_incomplete[, c("Temperature", "Cloudcoverage", "Windspeed", "Weight_ind", "Traject100m")]
source("~/GitHub/vespa_analyses/Input/HighstatLibV10.R")
corvif(datacor)##
##
## Variance inflation factors
##
## GVIF
## Temperature 6.054309
## Cloudcoverage 1.354508
## Windspeed 1.330242
## Weight_ind 1.441363
## Traject100m 6.708611cormat <- round(cor(datacor, use = "pairwise.complete.obs"), 2)
ggcorrplot(cormat, lab= TRUE, type = "lower", ggtheme = ggplot2::theme_gray,
colors = c("#6D9EC1", "white", "#E46726"))
plot(Temperature~Traject100m, data=Flights2_incomplete)
Eerder toeval dat Temperature en Traject100m gecorreleeerd zijn?
##PCA
library(vegan)## Loading required package: permute## Loading required package: lattice## This is vegan 2.6-4library(missMDA)
library(FactoMineR)
datapca<-select(Flights2_incomplete, Cloudcoverage, Windspeed, Temperature, Weight_ind, Traject100m)
nb <- estim_ncpPCA(datapca, scale = TRUE)
comp<-imputePCA(datapca, ncp=2)
res<-PCA(comp$completeObs)
